Instructions to use BiliSakura/PixNerd-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/PixNerd-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/PixNerd-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- PixNerd-XL-16-512/README.md +6 -0
- PixNerd-XL-16-512/demo.png +3 -0
- README.md +10 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
PixNerd-XL-16-512/demo.png filter=lfs diff=lfs merge=lfs -text
|
PixNerd-XL-16-512/README.md
CHANGED
|
@@ -39,3 +39,9 @@ images = pipe(
|
|
| 39 |
order=2,
|
| 40 |
).images
|
| 41 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
order=2,
|
| 40 |
).images
|
| 41 |
```
|
| 42 |
+
|
| 43 |
+
## Demo
|
| 44 |
+
|
| 45 |
+

|
| 46 |
+
|
| 47 |
+
Class 207 — golden retriever / 金毛猎犬, 512×512, 25 steps.
|
PixNerd-XL-16-512/demo.png
ADDED
|
Git LFS Details
|
README.md
CHANGED
|
@@ -1,12 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
library_name: diffusers
|
|
|
|
| 4 |
tags:
|
| 5 |
- diffusers
|
| 6 |
- image-generation
|
| 7 |
- class-conditional
|
| 8 |
- imagenet
|
| 9 |
- pixnerd
|
|
|
|
|
|
|
|
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
---
|
|
@@ -31,6 +35,12 @@ This Hugging Face repo hosts **multiple self-contained checkpoints as subfolders
|
|
| 31 |
|
| 32 |
Both checkpoints are ImageNet class-conditional PixNerd-XL/16 exports with flow-matching sampling.
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
## ImageNet class labels
|
| 35 |
|
| 36 |
ImageNet-1k labels live in shared [`labels/`](labels/) at the repo root (not duplicated per variant). Format follows Hugging Face / DiT convention:
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
library_name: diffusers
|
| 4 |
+
pipeline_tag: text-to-image
|
| 5 |
tags:
|
| 6 |
- diffusers
|
| 7 |
- image-generation
|
| 8 |
- class-conditional
|
| 9 |
- imagenet
|
| 10 |
- pixnerd
|
| 11 |
+
widget:
|
| 12 |
+
- output:
|
| 13 |
+
url: PixNerd-XL-16-512/demo.png
|
| 14 |
language:
|
| 15 |
- en
|
| 16 |
---
|
|
|
|
| 35 |
|
| 36 |
Both checkpoints are ImageNet class-conditional PixNerd-XL/16 exports with flow-matching sampling.
|
| 37 |
|
| 38 |
+
## Demo
|
| 39 |
+
|
| 40 |
+

|
| 41 |
+
|
| 42 |
+
Class 207 — golden retriever / 金毛猎犬, 512×512, 25 steps.
|
| 43 |
+
|
| 44 |
## ImageNet class labels
|
| 45 |
|
| 46 |
ImageNet-1k labels live in shared [`labels/`](labels/) at the repo root (not duplicated per variant). Format follows Hugging Face / DiT convention:
|